client = AsyncAzureOpenAI( api_key=os.getenv("AZURE_OPENAI_API_KEY"), api_version=os.getenv("AZURE_OPENAI_API_VERSION"), azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT"), ) model = OpenAIChatCompletionsModel( model='gpt-4.1', openai_client=client, ) agent=Agent( name="Agent", instructions=base_instructions, model=model, model_settings=ModelSettings( parallel_tool_calls=False, temperature=0.8 ), ) # Run streaming process result = Runner.run_streamed( starting_agent=agent, input=enhanced_message, context=chat_context, max_turns=max_turns, run_config=run_config, ) logger.info(f"Start stream events") async for event in result.stream_events(): if event.type == "raw_response_event": if isinstance(event.data, ResponseTextDeltaEvent): pass elif event.type == "run_item_stream_event": if event.item.type == "tool_call_item": logger.info(f"--- Tool Call: {event.item.raw_item.name} ---") logger.info(f"Tool Call Full Info: {event.item.raw_item}") elif event.item.type == "tool_call_output_item": logger.info("--- Tool Call Result ---") # Ensure output is string type output_str = str(event.item.output) # Only log first 1000 chars logger.info(output_str[:1000]) logger.info("**Stream successfully finished") logger.info(f"**Final agent name: [{result.last_agent.name}]") final_output = result.final_output final_output_type = type(final_output) logger.info(f"**Final output type: [{final_output_type}]") logger.info(f"**Final output: [{final_output}]") if final_output is None: logger.error("**Final output is None") raise NoneDataError(detail="Final output is None") logger.info("**Token usage:") total_input_tokens = 0 total_output_tokens = 0 total_tokens = 0 for index, r in enumerate(result.raw_responses): logger.info( f"{index}: input_tokens: [{r.usage.input_tokens}], output_tokens: [{r.usage.output_tokens}], total_tokens: [{r.usage.total_tokens}]" ) total_input_tokens += r.usage.input_tokens total_output_tokens += r.usage.output_tokens total_tokens += r.usage.total_tokens logger.info( f"**Total input tokens: [{total_input_tokens}], total output tokens: [{total_output_tokens}], total tokens: [{total_tokens}]" )